fix(openai): tighten responses stream account tests

backend/internal/service/openai_gateway_service_test.go

@@ -1336,6 +1336,41 @@ func TestOpenAIStreamingPassthroughResponseDoneWithoutDoneMarkerStillSucceeds(t
 	require.Equal(t, 1, result.usage.CacheReadInputTokens)
 }
 
+func TestOpenAIStreamingPassthroughResponseIncompleteWithoutDoneMarkerStillSucceeds(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	cfg := &config.Config{
+		Gateway: config.GatewayConfig{
+			MaxLineSize: defaultMaxLineSize,
+		},
+	}
+	svc := &OpenAIGatewayService{cfg: cfg}
+
+	rec := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(rec)
+	c.Request = httptest.NewRequest(http.MethodPost, "/", nil)
+
+	pr, pw := io.Pipe()
+	resp := &http.Response{
+		StatusCode: http.StatusOK,
+		Body:       pr,
+		Header:     http.Header{},
+	}
+
+	go func() {
+		defer func() { _ = pw.Close() }()
+		_, _ = pw.Write([]byte("data: {\"type\":\"response.incomplete\",\"response\":{\"usage\":{\"input_tokens\":2,\"output_tokens\":3,\"input_tokens_details\":{\"cached_tokens\":1}}}}\n\n"))
+	}()
+
+	result, err := svc.handleStreamingResponsePassthrough(c.Request.Context(), resp, c, &Account{ID: 1}, time.Now(), "", "")
+	_ = pr.Close()
+	require.NoError(t, err)
+	require.NotNil(t, result)
+	require.NotNil(t, result.usage)
+	require.Equal(t, 2, result.usage.InputTokens)
+	require.Equal(t, 3, result.usage.OutputTokens)
+	require.Equal(t, 1, result.usage.CacheReadInputTokens)
+}
+
 func TestOpenAIStreamingTooLong(t *testing.T) {
 	gin.SetMode(gin.TestMode)
 	cfg := &config.Config{